{"id":3289577,"url":"https://alion.io/job/lumiq-senior-data-engineer-python-pandas-numpy","title":"Senior Data Engineer (Python, Pandas & Numpy)","company":{"id":679499,"name":"LumiQ","domain":"lumiqlearn.com","url":"https://alion.io/company/lumiqlearn","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Lever","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":"senior","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"inferred_company_offices","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":[],"countries":[],"hiring_countries":["IN"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":86000,"max_usd":193000,"period":"year","method":"global_role_seniority_cell","sample_n":2679},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Docker","optional":false},{"name":"ElasticSearch","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Kubernetes","optional":false},{"name":"MS SQL","optional":false},{"name":"NumPy","optional":false},{"name":"Pandas","optional":false},{"name":"Polars","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Python","optional":false},{"name":"SQL","optional":false}],"status":"live","first_seen_at":"2026-10-12T04:34:24Z","employer_posted_date":null,"last_verified_at":"2026-10-12T04:34:24Z","board_verified":false,"closed_at":null,"days_open":21,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":21},"description":"Job Purpose :\nWe are seeking a highly skilled ETL Data Engineer to re-engineer our existing data pipelines to extract data from a new data source (PostgreSQL / CURA system) instead of the current Microsoft SQL Server (CRM persistence store), while preserving the existing load patterns to Elasticsearch and MongoDB. The engineer will ensure this migration has zero impact on data quality, system performance, or end-user experience.\nKey Responsibilities :\n- Analyze existing ETL pipelines and their dependencies on Microsoft SQL Server as source systems.\n\nDesign and implement modifications to repoint ETL extractions from PostgreSQL (CURA) while preserving the current transformations and load logic into Elasticsearch and MongoDB.\n\nEnsure end-to-end data integrity, quality, and freshness remain unaffected after the source switch.\n\nWrite efficient and optimized SQL queries to extract data from the new source.\n\nConduct performance testing to confirm no degradation of pipeline throughput or latency in production.\n\nWork closely with DevOps and platform teams to containerize, orchestrate, and deploy the updated ETLs using Docker and Kubernetes.\n\nMonitor post-deployment performance and handle any production issues proactively.\n\nDocument design, code, data mappings, and operational runbooks.\n\nRequired Skills and Qualifications :\n\nStrong experience building and maintaining large-scale distributed data systems.\n- Expert-level proficiency in Python, especially data analysis/manipulation libraries like pandas, NumPy, and Polars.\n\nAdvanced SQL development skills with proven experience in performance optimization.\n\nWorking knowledge of Docker and Kubernetes.\n\nFamiliarity with Elasticsearch and MongoDB as data stores.\n\nExperience working in production environments with mission-critical systems.\n\nOriginally posted on Himalayas","description_format":"text","description_chars":1835,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"India","iso":"IN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Continuing Education","Podcasting"],"lifecycle":[{"event":"open","at":"2026-10-26T19:11:04Z"}],"visa":[{"country":"CA","licensed_sponsor":true,"evidence":"Approved LMIA in the last two years","filings_12m":0,"filings_prev_12m":1,"green_card_filings_12m":null,"median_offered_wage_usd":null,"route":null,"cap_exempt":false,"checked_at":"2026-10-03T21:10:52+00:00","sources":["ESDC: employers issued a positive LMIA"],"filings_for_role_12m":0}],"liveness":{"score":69,"band":"ok","label":"Likely open","p_open":0.85,"p_active":0.903,"p_room":0.9,"age_days":21,"expected_fill_days":35,"reasons":["seen:21","velocity","win:mid"],"computed_at":"2026-11-02T06:13:15Z"},"pay":null,"html_url":"https://alion.io/job/lumiq-senior-data-engineer-python-pandas-numpy","json_url":"https://alion.io/job/lumiq-senior-data-engineer-python-pandas-numpy.json","meta":{"generated_at":"2026-11-02T11:15:33Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":15490,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-03T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":679499},"rest":"https://alion.io/mcp/rest/get_company?id=679499"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Flumiq-senior-data-engineer-python-pandas-numpy"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Flumiq-senior-data-engineer-python-pandas-numpy"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Flumiq-senior-data-engineer-python-pandas-numpy"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/lumiq-senior-data-engineer-python-pandas-numpy\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Flumiq-senior-data-engineer-python-pandas-numpy"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3289577}},{"tool":"search_jobs","arguments":{"company":"lumiqlearn.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3289577},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}